© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3625
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology procedures and technical instructions

    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
    478
    +0.15
    0.4%
    658
    +0.13
    0.4%
    1381
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    658
    +0.15
    0.08
    47
    +0.13
    0.05
    478
    +0.10
    0.05
    Negative Logits
    ₁,
    -0.49
    lamic
    -0.49
    madeus
    -0.49
    pfe
    -0.48
     fédé
    -0.47
     Suivez
    -0.47
     malheureux
    -0.47
     décid
    -0.46
     cahier
    -0.46
     [''
    -0.45
    POSITIVE LOGITS
    Siamo
    0.67
     esternos
    0.64
    Preparazione
    0.62
     able
    0.59
     dichi
    0.58
     lucky
    0.58
    Переваги
    0.57
    ánchez
    0.57
    Oggi
    0.56
    GEBURTSDATUM
    0.55
    Activations Density 0.265%

    No Known Activations