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. 15876
    Prev
    Next
    INDEX
    Explanations

    numerical values or measurements related to counting or scoring

    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
    1496
    +0.11
    0.3%
    2006
    +0.08
    0.2%
    855
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1496
    +0.11
    0.05
    1243
    +0.08
    0.05
    948
    +0.08
    0.04
    Negative Logits
     trast
    -0.81
     ananas
    -0.80
     utop
    -0.79
     Juf
    -0.78
     fré
    -0.77
     augus
    -0.77
     Keny
    -0.77
     kram
    -0.76
     socie
    -0.75
     persil
    -0.74
    POSITIVE LOGITS
     devoted
    0.60
     gone
    0.55
     actually
    0.55
     reserved
    0.54
     overlap
    0.53
     taken
    0.53
     consists
    0.53
     câteva
    0.52
     accounted
    0.52
     comes
    0.52
    Activations Density 0.339%

    No Known Activations