© 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. 1002
    Prev
    Next
    INDEX
    Explanations

    declarative statements or key points in long narrations

    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
    1042
    +0.10
    0.3%
    1306
    +0.09
    0.3%
    1108
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    475
    +0.10
    0.03
    814
    +0.09
    0.02
    929
    +0.09
    0.03
    Negative Logits
     perpé
    -0.77
     puto
    -0.70
     derni
    -0.69
    tionally
    -0.66
     proprement
    -0.65
     exé
    -0.64
     adoro
    -0.63
     territo
    -0.63
     tendre
    -0.63
     rarement
    -0.63
    POSITIVE LOGITS
    ValueStyle
    0.66
     point
    0.65
     juncture
    0.64
    point
    0.59
    OURCE
    0.58
     Point
    0.54
    Point
    0.53
     POINT
    0.53
     moment
    0.52
    POINT
    0.52
    Activations Density 0.103%

    No Known Activations