Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14718
    Prev
    Next
    INDEX
    Explanations

    mentions of historical events and organizational structures

    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
    1150
    +0.14
    0.4%
    1535
    +0.12
    0.4%
    1577
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    580
    +0.14
    0.06
    1170
    +0.12
    0.06
    163
    +0.11
    0.04
    Negative Logits
    Obrigado
    -0.68
    Și
    -0.65
    astéro
    -0.64
     himo
    -0.64
    Estou
    -0.62
    Personendaten
    -0.62
    Parabéns
    -0.62
    extAlignment
    -0.61
    Conteúdo
    -0.60
     naselje
    -0.60
    POSITIVE LOGITS
     disagre
    1.01
     maneu
    0.99
     suscep
    0.93
     reluct
    0.93
     interposed
    0.93
     unve
    0.89
     accla
    0.85
     wherea
    0.84
     inappro
    0.84
     !...
    0.83
    Activations Density 0.178%

    No Known Activations