© 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. 7752
    Prev
    Next
    INDEX
    Explanations

    information about specific numerical counts or statistics

    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
    776
    +0.16
    0.6%
    1678
    +0.10
    0.4%
    1124
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1124
    +0.16
    0.05
    776
    +0.10
    0.06
    537
    +0.10
    0.05
    Negative Logits
     nuage
    -0.65
     bénéficiaire
    -0.61
     basque
    -0.61
     avancée
    -0.61
     décal
    -0.60
     fondateur
    -0.60
     vieille
    -0.59
     intermédiaire
    -0.59
     venerdì
    -0.59
     princesse
    -0.59
    POSITIVE LOGITS
    ONE
    0.87
     one
    0.86
     ONE
    0.85
    one
    0.84
    One
    0.81
     One
    0.77
    getOne
    0.67
    Ones
    0.58
    Satu
    0.57
     uno
    0.56
    Activations Density 0.174%

    No Known Activations