© 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. 12865
    Prev
    Next
    INDEX
    Explanations

    quotations or dialogue

    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
    604
    +0.14
    0.4%
    2034
    +0.13
    0.4%
    1253
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    19
    +0.14
    0.08
    1533
    +0.13
    0.05
    1509
    +0.11
    0.07
    Negative Logits
     intersper
    -1.45
     cushi
    -1.43
     hairc
    -1.42
     swarovski
    -1.36
     shenan
    -1.35
     scrat
    -1.34
     disreg
    -1.34
     impra
    -1.29
     impractica
    -1.27
     snoopy
    -1.25
    POSITIVE LOGITS
     silikon
    1.06
     alkoh
    1.04
     katastro
    1.02
     demokra
    1.02
     kosme
    0.97
     optik
    0.97
     mikrofon
    0.95
     seksi
    0.95
     Meksiko
    0.95
     Demokrat
    0.95
    Activations Density 0.385%

    No Known Activations