© 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. 5162
    Prev
    Next
    INDEX
    Explanations

    descriptions related to writing materials and tools

    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
    +0.21
    0.8%
    1150
    +0.11
    0.4%
    678
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.21
    0.06
    783
    +0.11
    0.04
    1305
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.59
    Vegeu
    -0.65
     للاسماء
    -0.65
    IActionResult
    -0.61
    HasIndex
    -0.60
    Configurer
    -0.60
    EndContext
    -0.60
     AssemblyCompany
    -0.58
    displayquote
    -0.58
    SerializedSize
    -0.57
    POSITIVE LOGITS
     bandung
    1.56
     maroc
    1.47
     lele
    1.40
     Minang
    1.34
     maneu
    1.26
     siena
    1.26
     jawa
    1.24
     quoc
    1.22
     surabaya
    1.22
     kaos
    1.19
    Activations Density 0.576%

    No Known Activations