© 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. 0-RES-JB
    6. 851
    Prev
    Next
    INDEX
    Explanations

    mentions of events or places

    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
    486
    +0.09
    0.2%
    75
    +0.08
    0.2%
    1256
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.09
    0.04
    1363
    +0.08
    0.03
    773
    +0.07
    0.02
    Negative Logits
    ⓧ
    -0.76
    /**
    -0.72
    /*
    -0.67
     assailed
    -0.65
     arranges
    -0.63
    #
    -0.62
     intervened
    -0.61
     whistled
    -0.61
     forbade
    -0.61
    <?
    -0.60
    POSITIVE LOGITS
    umb
    3.20
    UMB
    2.11
    umba
    1.41
     bumb
    1.37
     Lombar
    1.32
     umb
    1.24
     abbra
    1.22
     lomb
    1.20
     tumb
    1.17
     autob
    1.17
    Activations Density 0.239%

    No Known Activations