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. 15580
    Prev
    Next
    INDEX
    Explanations

    references to checking something out or exploring further

    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
    678
    +0.15
    0.5%
    690
    +0.12
    0.4%
    597
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.15
    0.02
    442
    +0.12
    0.02
    597
    +0.11
    0.02
    Negative Logits
    espé
    -0.59
    Argumento
    -0.58
    Trayectoria
    -0.56
     febr
    -0.56
    loài
    -0.56
    обходи
    -0.56
    Componentes
    -0.56
    fatalError
    -0.56
    Hochspringen
    -0.55
    NSUserDefaults
    -0.55
    POSITIVE LOGITS
     Sampled
    0.95
     Proofs
    0.89
     Checkout
    0.87
     Derivation
    0.79
     outlander
    0.74
     unspeak
    0.74
     cuck
    0.73
     Varies
    0.73
     Cæsar
    0.73
     resemb
    0.73
    Activations Density 0.049%

    No Known Activations