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. 15577
    Prev
    Next
    INDEX
    Explanations

    scientific research related to neuroscience and endocrinology

    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
    1343
    +0.15
    0.5%
    1499
    +0.11
    0.3%
    283
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    924
    +0.15
    0.04
    1784
    +0.11
    0.03
    1343
    +0.09
    0.03
    Negative Logits
     ecru
    -0.85
     sceptre
    -0.83
     Shakspeare
    -0.78
     boughs
    -0.76
     tupperware
    -0.70
     frock
    -0.70
     pettico
    -0.69
     McLaugh
    -0.69
     withal
    -0.68
     McInt
    -0.66
    POSITIVE LOGITS
     reger
    0.71
     handels
    0.69
    IInter
    0.65
     tille
    0.64
     hals
    0.64
     psycholog
    0.59
     sogget
    0.59
     bergen
    0.59
     gius
    0.57
     vermel
    0.57
    Activations Density 0.244%

    No Known Activations