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. 24-GEMMASCOPE-RES-16K
    6. 12691
    Prev
    Next
    INDEX
    Explanations

    relationships and connections between family members

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

    Punctuation followed by other tokens

    np_acts-logits-general · gemini-2.0-flash

    .NET framework or code snippets

    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
    mybatisplus
    -0.66
     חיצוניים
    -0.61
    mapStateToProps
    -0.59
    protoc
    -0.57
    Naissance
    -0.54
     Paglinawan
    -0.53
    ManagedBean
    -0.53
    ésultat
    -0.53
     marginBottom
    -0.53
    ership
    -0.52
    POSITIVE LOGITS
     Relatives
    0.64
    Visiting
    0.58
    aarrggbb
    0.56
     Visiting
    0.56
     فريبيس
    0.54
     OMIT
    0.52
     Calling
    0.52
    RenderAtEndOf
    0.52
    Calling
    0.51
    JSONException
    0.51
    Activations Density 0.078%

    No Known Activations