© 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. 13697
    Prev
    Next
    INDEX
    Explanations

    dollar amounts or percentages mentioned in the context

    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
    1978
    +0.19
    0.6%
    453
    +0.13
    0.4%
    776
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.19
    0.05
    776
    +0.13
    0.05
    815
    +0.09
    0.04
    Negative Logits
     vœ
    -0.93
     suscep
    -0.91
     indestru
    -0.90
     intersper
    -0.89
     beaute
    -0.88
     outlander
    -0.88
     élégante
    -0.85
     hairc
    -0.85
     reconno
    -0.84
     vagu
    -0.84
    POSITIVE LOGITS
     kafe
    0.85
     krim
    0.83
     bakar
    0.82
     karton
    0.78
     keramik
    0.77
     karbon
    0.76
     ekos
    0.76
     kristal
    0.76
     klinik
    0.76
     bunda
    0.74
    Activations Density 0.165%

    No Known Activations