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. 8375
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational policies and government initiatives

    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
    1253
    +0.13
    0.4%
    1823
    +0.10
    0.3%
    717
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1823
    +0.13
    0.04
    644
    +0.10
    0.06
    841
    +0.10
    0.02
    Negative Logits
     hornblende
    -0.58
     anhyd
    -0.58
     EXERCISES
    -0.58
     WALTZ
    -0.56
     ILLUSTRATIONS
    -0.54
     STUART
    -0.53
     calyx
    -0.53
     gneiss
    -0.52
     doublet
    -0.52
     HERBERT
    -0.52
    POSITIVE LOGITS
     schools
    0.86
     Kalifor
    0.85
     silikon
    0.84
     Schools
    0.76
     school
    0.74
     karton
    0.74
     Spani
    0.73
     GreatSchools
    0.72
     optik
    0.72
     alkoh
    0.72
    Activations Density 0.708%

    No Known Activations