© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7572
    Prev
    Next
    INDEX
    Explanations

    specific technical actions and equipment related to manual operation

    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
    946
    +0.15
    0.4%
    678
    +0.14
    0.4%
    1385
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.15
    0.09
    946
    +0.14
    0.07
    1385
    +0.13
    0.06
    Negative Logits
     protokol
    -0.76
     minimalis
    -0.76
    DataPropertyName
    -0.71
     bera
    -0.69
     kosme
    -0.68
     kalori
    -0.67
     kado
    -0.67
    expandindo
    -0.67
     panik
    -0.66
     kemer
    -0.66
    POSITIVE LOGITS
     triomphe
    0.90
     disreg
    0.89
     considér
    0.88
     écout
    0.87
     regardant
    0.85
     pym
    0.84
     parlant
    0.84
     échange
    0.82
     évit
    0.81
     dégust
    0.79
    Activations Density 0.699%

    No Known Activations