© 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. 14219
    Prev
    Next
    INDEX
    Explanations

    terms related to historical concepts like "decades," "centuries," and "old."

    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
    198
    +0.19
    0.6%
    674
    +0.11
    0.3%
    876
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.19
    0.07
    198
    +0.11
    0.06
    1615
    +0.09
    0.06
    Negative Logits
     wattpad
    -0.73
     potranno
    -0.69
     dovrebbero
    -0.69
     sembrano
    -0.68
     abbiano
    -0.67
     conç
    -0.66
     eqn
    -0.64
     lakers
    -0.63
     dicono
    -0.60
     Bucure
    -0.60
    POSITIVE LOGITS
     accepte
    0.60
     étu
    0.54
     cze
    0.53
     kurios
    0.53
     vulgares
    0.53
     serem
    0.53
     germain
    0.52
    require
    0.51
    espo
    0.50
     are
    0.50
    Activations Density 0.651%

    No Known Activations