© 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. 14554
    Prev
    Next
    INDEX
    Explanations

    locations or names of specific places

    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
    50
    +0.27
    0.8%
    1062
    +0.07
    0.2%
    1870
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.27
    0.13
    507
    +0.07
    0.08
    964
    +0.07
    0.07
    Negative Logits
     Tampoco
    -0.69
    Quelles
    -0.69
    municipi
    -0.65
     Hvad
    -0.64
     poichè
    -0.63
    bardziej
    -0.62
    Și
    -0.62
     acred
    -0.61
     contactez
    -0.61
    Dziękuję
    -0.61
    POSITIVE LOGITS
     vry
    0.73
     deere
    0.72
     daz
    0.70
     blos
    0.67
     wein
    0.66
     alre
    0.66
     fto
    0.66
     Realt
    0.65
     bauer
    0.63
     zimmer
    0.63
    Activations Density 1.478%

    No Known Activations