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. 15850
    Prev
    Next
    INDEX
    Explanations

    proper nouns and technical terms related to business and technology

    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
    198
    +0.11
    0.3%
    1343
    +0.09
    0.3%
    845
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1432
    +0.11
    0.04
    198
    +0.09
    0.05
    287
    +0.07
    0.05
    Negative Logits
     alkoh
    -0.74
     katal
    -0.71
     solidar
    -0.70
     erk
    -0.70
     antik
    -0.67
     Kategor
    -0.66
     plak
    -0.65
     radikal
    -0.65
     kosme
    -0.64
     متعلقه
    -0.64
    POSITIVE LOGITS
     cushi
    0.78
    relenting
    0.75
     rodriguez
    0.75
    sightly
    0.73
     affor
    0.73
     disreg
    0.73
     rafael
    0.72
     curé
    0.70
    ⓧ
    0.70
     împre
    0.70
    Activations Density 0.497%

    No Known Activations