© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 2949
    Prev
    Next
    INDEX
    Explanations

    affirmations and statements about existence or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "is/are/were supposed" or similar phrases

    np_acts-logits-general · gemini-2.0-flash

    is/are/were followed by a state or action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cshtml
    -0.71
    lifier
    -0.58
    UnusedPrivate
    -0.56
    osomal
    -0.54
     orgánico
    -0.53
     Portail
    -0.52
    nelli
    -0.52
    اں
    -0.52
    orexia
    -0.51
     erle
    -0.51
    POSITIVE LOGITS
     supposed
    1.10
    supposed
    0.83
     CreateTagHelper
    0.78
     meant
    0.74
     willing
    0.70
     capable
    0.70
     gonna
    0.69
     able
    0.68
     suppose
    0.65
     going
    0.64
    Activations Density 0.113%

    No Known Activations