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. 8214
    Prev
    Next
    INDEX
    Explanations

    information related to computer hardware specifications

    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
    1741
    +0.12
    0.4%
    86
    +0.11
    0.3%
    1978
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.12
    0.03
    1110
    +0.11
    0.02
    438
    +0.11
    0.03
    Negative Logits
     gius
    -0.88
     chied
    -0.83
     LXXX
    -0.83
     ridu
    -0.81
     doveva
    -0.81
     faceva
    -0.81
     partecipa
    -0.79
     viciss
    -0.79
     abbra
    -0.79
     espri
    -0.78
    POSITIVE LOGITS
    GB
    0.63
    MB
    0.56
     GB
    0.56
     capacity
    0.51
     of
    0.50
    gb
    0.50
     MB
    0.49
    KB
    0.47
    bs
    0.45
    abytes
    0.44
    Activations Density 0.089%

    No Known Activations