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. 8246
    Prev
    Next
    INDEX
    Explanations

    annotated diagrams in scientific contexts or presentations

    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
    906
    +0.14
    0.4%
    1343
    +0.12
    0.4%
    1385
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1856
    +0.14
    0.04
    906
    +0.12
    0.00
    1082
    +0.12
    0.02
    Negative Logits
     republi
    -0.75
     klap
    -0.74
     nabi
    -0.72
     deko
    -0.71
     katal
    -0.71
     radikal
    -0.70
     Rektor
    -0.70
     kaos
    -0.69
     optik
    -0.69
     stik
    -0.69
    POSITIVE LOGITS
     impractica
    0.68
     arrows
    0.62
     McLaugh
    0.60
     MATHEMATICAL
    0.59
     pamph
    0.59
    Cringe
    0.59
    Throwaway
    0.56
     unve
    0.55
     unwarran
    0.54
    Ehh
    0.54
    Activations Density 0.173%

    No Known Activations