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. 8256
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions or features of a product or service

    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
    876
    +0.09
    0.3%
    441
    +0.09
    0.2%
    1252
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.09
    0.04
    1859
    +0.09
    0.02
    1368
    +0.08
    0.02
    Negative Logits
    LookAnd
    -0.69
    GEBURTSDATUM
    -0.65
    Televis
    -0.65
     hadas
    -0.63
     Rumuni
    -0.63
    Хьажоргаш
    -0.61
    Filmo
    -0.60
    Forrás
    -0.60
    Geografi
    -0.59
     lenker
    -0.59
    POSITIVE LOGITS
     shenan
    1.18
     snoopy
    1.08
     hairc
    1.08
     intersper
    1.07
     sophistic
    1.01
     simpsons
    1.01
     encomp
    1.00
     apprehen
    1.00
     depic
    0.98
     wikihow
    0.98
    Activations Density 0.701%

    No Known Activations