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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 4693
    Prev
    Next
    INDEX
    Explanations

    technical terms related to networking and configurations

    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
    1499
    +0.14
    0.6%
    1577
    +0.11
    0.5%
    876
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1577
    +0.14
    0.30
    1385
    +0.11
    0.24
    678
    +0.11
    0.21
    Negative Logits
    <bos>
    -2.86
    <?
    -0.80
     de
    -0.79
    ↵↵
    -0.77
    .
    -0.77
     can
    -0.74
    ;
    -0.74
     also
    -0.74
     Im
    -0.73
     أيضاً
    -0.73
    POSITIVE LOGITS
     tramont
    2.13
     wien
    2.12
     napoli
    2.11
     bandung
    2.10
     milano
    2.06
     fluo
    2.05
     fatis
    1.98
     mef
    1.95
     maer
    1.95
     sappi
    1.95
    Activations Density 11.688%

    No Known Activations