© 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. 14326
    Prev
    Next
    INDEX
    Explanations

    references to specific areas or regions, especially in the context of politics or sports

    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
    1276
    +0.13
    0.5%
    667
    +0.13
    0.5%
    1870
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1276
    +0.13
    0.02
    868
    +0.13
    0.02
    101
    +0.12
    0.02
    Negative Logits
     Décembre
    -0.76
     Ottobre
    -0.74
     assiste
    -0.71
     milano
    -0.69
     fumo
    -0.69
     biex
    -0.68
     ?...
    -0.68
     Bâ
    -0.67
     ivi
    -0.67
     tramont
    -0.67
    POSITIVE LOGITS
     zone
    1.53
     Zone
    1.42
    zone
    1.41
     zones
    1.40
    Zone
    1.27
     ZONE
    1.27
     Zones
    1.24
    ZONE
    1.19
    zones
    1.19
    ZoneId
    0.99
    Activations Density 0.061%

    No Known Activations