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. 8421
    Prev
    Next
    INDEX
    Explanations

    information about a detailed organizational or political plan

    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
    1120
    +0.19
    0.6%
    1511
    +0.18
    0.6%
    1499
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.19
    0.11
    1511
    +0.18
    0.02
    1216
    +0.15
    0.08
    Negative Logits
     jaya
    -1.10
     kayo
    -1.10
     makita
    -1.05
     krishna
    -1.03
     flyknit
    -0.94
     aspetta
    -0.89
     jati
    -0.85
     muna
    -0.84
     bago
    -0.84
     hapa
    -0.82
    POSITIVE LOGITS
     Bartholo
    1.05
     Simult
    0.91
     Gorb
    0.89
     Rued
    0.85
     Pott
    0.85
     Reim
    0.84
     Oester
    0.84
     Rine
    0.83
     Rodrig
    0.82
     Diez
    0.82
    Activations Density 1.577%

    No Known Activations