© 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. 3811
    Prev
    Next
    INDEX
    Explanations

    terms related to cultural and historical figures or events

    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
    204
    +0.16
    0.6%
    1480
    +0.14
    0.6%
    1437
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.16
    0.03
    981
    +0.14
    0.05
    1480
    +0.13
    0.04
    Negative Logits
    Probl
    -0.57
    Schwer
    -0.52
    loài
    -0.51
    IndentedString
    -0.49
    asteroide
    -0.49
    Demografía
    -0.48
    Få
    -0.48
    Från
    -0.47
    Polen
    -0.47
    Tentang
    -0.46
    POSITIVE LOGITS
     depic
    1.40
     maneu
    1.38
     strick
    1.33
     milf
    1.32
     increa
    1.31
     affor
    1.30
     intersper
    1.29
     scrat
    1.26
     shenan
    1.26
     disagre
    1.25
    Activations Density 0.205%

    No Known Activations