© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 5100
    Prev
    Next
    INDEX
    Explanations

    words related to specific medical conditions, such as arthritis and pigment deposits like ochronotic pigment

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    478
    +0.17
    0.8%
    605
    +0.13
    0.6%
    50
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.17
    0.10
    478
    +0.13
    0.05
    468
    +0.11
    0.07
    Negative Logits
    <bos>
    -2.61
    DockStyle
    -0.93
    AsUp
    -0.88
    addPreferredGap
    -0.84
    Unmarshaller
    -0.81
    orElseThrow
    -0.80
    HasColumnType
    -0.79
    InitStruct
    -0.79
    migrationBuilder
    -0.78
    WireFormat
    -0.78
    POSITIVE LOGITS
     napoli
    2.26
     milano
    2.08
     stockholm
    2.05
     toledo
    2.05
     Augu
    2.02
     lidl
    1.99
    fordable
    1.97
     reluct
    1.97
     frankfurt
    1.95
     increa
    1.95
    Activations Density 0.842%

    No Known Activations