© 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. 14344
    Prev
    Next
    INDEX
    Explanations

    mentions related to traffic regulations, specific medical conditions affecting fish, and specific incidents in a news report

    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
    1385
    +0.11
    0.3%
    1856
    +0.09
    0.3%
    1097
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1856
    +0.11
    0.09
    1870
    +0.09
    0.04
    694
    +0.08
    0.05
    Negative Logits
     overla
    -0.99
     blin
    -0.92
     nutr
    -0.89
     tass
    -0.89
     rege
    -0.88
     dispen
    -0.87
     regis
    -0.84
     illi
    -0.84
     baf
    -0.84
     ciao
    -0.83
    POSITIVE LOGITS
     tanong
    0.69
     utaf
    0.67
    Lmfao
    0.66
     habang
    0.60
     potentialities
    0.60
     pagkak
    0.59
     EEU
    0.58
    widetext
    0.57
     Shakspeare
    0.56
     BSEB
    0.56
    Activations Density 0.892%

    No Known Activations