© 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. 0-RES-JB
    11. 2426
    Prev
    Next
    INDEX
    Explanations

    HTML code related to creating links

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    919
    +0.12
    0.3%
    828
    +0.09
    0.3%
    789
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.12
    0.03
    1343
    +0.09
    0.03
    283
    +0.08
    0.00
    Negative Logits
     cytoplas
    -0.65
    =""></
    -0.62
     Gallimard
    -0.60
     mitochond
    -0.57
     gilet
    -0.56
     Mónica
    -0.55
     Katja
    -0.55
    \"></
    -0.55
    "]).
    -0.54
    __]
    -0.53
    POSITIVE LOGITS
    ="
    1.58
    =”
    1.14
    ="_
    1.13
    ='
    1.10
    =\"
    1.01
    ="-
    0.97
    )="
    0.85
    ="/
    0.82
    ="+
    0.80
    ="@
    0.78
    Activations Density 0.266%

    No Known Activations