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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 9757
    Prev
    Next
    INDEX
    Explanations

    references to female characters and their representation in narratives

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

    after quotations or related to movies

    np_acts-logits-general · gemini-2.0-flash

    actors and characters in shows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.61
    …(
    -0.56
     abstrato
    -0.54
    …’
    -0.54
    __(/*!
    -0.51
     CreateTagHelper
    -0.51
    ător
    -0.50
    PhysRevD
    -0.49
    ellingham
    -0.49
    hastly
    -0.49
    POSITIVE LOGITS
    PerformLayout
    0.65
     netizens
    0.62
     cp
    0.58
     }}"></
    0.57
    WebMethod
    0.57
     barrage
    0.55
     Reuters
    0.54
    campal
    0.53
    Advertisement
    0.53
     CP
    0.52
    Activations Density 0.038%

    No Known Activations