© 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. 3494
    Prev
    Next
    INDEX
    Explanations

    data analysis terminology and statistical methods

    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
    876
    +0.19
    0.6%
    1499
    +0.16
    0.5%
    1253
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.19
    0.06
    1652
    +0.16
    0.03
    876
    +0.13
    -0.01
    Negative Logits
     laity
    -0.52
     Thine
    -0.50
     Exchequer
    -0.49
     Whigs
    -0.48
     Episcop
    -0.46
     Presbyter
    -0.46
     clergymen
    -0.46
     Fascism
    -0.46
     Clergy
    -0.46
     Herrick
    -0.46
    POSITIVE LOGITS
     maneu
    1.19
     increa
    1.17
     overla
    1.15
     pessi
    1.10
     emphat
    1.10
     effe
    1.10
     disagre
    1.08
     perfon
    1.07
     mef
    1.06
     guarante
    1.05
    Activations Density 0.268%

    No Known Activations