© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3336
    Prev
    Next
    INDEX
    Explanations

    references to specific individual names or proper nouns

    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
    50
    +0.20
    0.7%
    1741
    +0.19
    0.7%
    1385
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.20
    0.10
    678
    +0.19
    0.08
    50
    +0.14
    0.07
    Negative Logits
     öf
    -0.65
    igts
    -0.62
     kontinu
    -0.57
     habang
    -0.57
    onlu
    -0.53
    hasErrors
    -0.52
     xxvi
    -0.52
    ffiti
    -0.51
     florales
    -0.51
    ochlor
    -0.50
    POSITIVE LOGITS
     entire
    0.76
     same
    0.73
     exact
    0.63
     entirety
    0.63
     aforementioned
    0.61
    Demikian
    0.61
    Wichtig
    0.61
    Mitä
    0.60
     necessary
    0.60
    Einige
    0.59
    Activations Density 0.530%

    No Known Activations