Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 1357
    Prev
    Next
    INDEX
    Explanations

    elements related to causal inference and counterfactual reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amaño
    -0.81
    KEYCODE
    -0.72
    umbersome
    -0.70
     itſelf
    -0.69
    UserScript
    -0.68
     PicClick
    -0.68
     ſy
    -0.68
    ſelf
    -0.68
     ſhould
    -0.67
     preſent
    -0.67
    POSITIVE LOGITS
    וויק
    0.67
    Decided
    0.55
     also
    0.51
    ’
    0.50
    quad
    0.50
     among
    0.49
    SuppressMessage
    0.48
    zer
    0.47
     mathvariant
    0.46
    be
    0.45
    Activations Density 3.372%

    No Known Activations