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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 359
    Prev
    Next
    INDEX
    Explanations

    descriptions and reviews of music albums and bands

    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
    50
    +0.20
    0.8%
    304
    +0.11
    0.4%
    108
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1136
    +0.20
    0.08
    304
    +0.11
    -0.07
    924
    +0.08
    0.12
    Negative Logits
    <bos>
    -2.85
    EndContext
    -0.88
    ContentAlignment
    -0.87
    {{--
    -0.84
    styleType
    -0.82
    WriteAttribute
    -0.82
    SequentialGroup
    -0.81
    titleMargin
    -0.81
    abetes
    -0.81
    }{||
    -0.81
    POSITIVE LOGITS
     maneu
    2.61
     affor
    2.60
     accla
    2.55
     reluct
    2.52
     impra
    2.51
     increa
    2.51
     indestru
    2.47
     inev
    2.43
     emphat
    2.42
     excru
    2.42
    Activations Density 2.815%

    No Known Activations