© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 2326
    Prev
    Next
    INDEX
    Explanations

    mentions of changes or transformations happening

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    161
    +0.11
    0.3%
    1984
    +0.11
    0.3%
    1129
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.11
    0.04
    161
    +0.11
    0.03
    220
    +0.10
    0.03
    Negative Logits
     nece
    -0.80
     inconce
    -0.78
     ingrat
    -0.72
     benevol
    -0.72
     desir
    -0.71
     shur
    -0.71
     thut
    -0.70
     trast
    -0.69
     Mlle
    -0.68
     disagre
    -0.68
    POSITIVE LOGITS
     Into
    0.73
     INTO
    0.72
     into
    0.71
    Into
    0.64
    into
    0.63
    become
    0.57
     a
    0.56
     become
    0.56
     something
    0.55
     BECOME
    0.54
    Activations Density 0.119%

    No Known Activations