© 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. 3390
    Prev
    Next
    INDEX
    Explanations

    mentions of notable people winning awards or accolades

    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
    453
    +0.18
    0.6%
    1842
    +0.18
    0.6%
    1343
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.18
    0.04
    510
    +0.18
    0.04
    599
    +0.18
    0.04
    Negative Logits
    Dlaczego
    -1.01
    Vlastnosti
    -1.00
    Jakie
    -0.97
    Zgod
    -0.94
    على
    -0.92
    Warto
    -0.92
    Czym
    -0.91
    Teraz
    -0.88
     in
    -0.87
     due
    -0.86
    POSITIVE LOGITS
     ciga
    2.71
     dispen
    2.67
     milano
    2.63
     franz
    2.62
     wien
    2.62
     nutr
    2.61
     inder
    2.60
     tanga
    2.59
     blin
    2.58
     ordina
    2.58
    Activations Density 0.321%

    No Known Activations