Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15682
    Prev
    Next
    INDEX
    Explanations

    terms related to awards, politics, and unique events

    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
    1535
    +0.18
    0.5%
    1870
    +0.14
    0.4%
    1842
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.18
    0.04
    845
    +0.14
    0.05
    324
    +0.11
    0.04
    Negative Logits
     melange
    -0.66
     Inhabitants
    -0.65
     Casanova
    -0.64
    omm
    -0.63
     Bergmann
    -0.61
    Antibodies
    -0.61
    uests
    -0.61
     wanderer
    -0.61
     earl
    -0.61
     celtic
    -0.60
    POSITIVE LOGITS
    rlrl
    0.84
     pagkak
    0.74
     apparti
    0.73
     parteci
    0.71
     furg
    0.70
     abbiano
    0.70
     vogli
    0.68
     soggior
    0.67
     tanong
    0.66
     trovo
    0.65
    Activations Density 0.871%

    No Known Activations