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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 52
    Prev
    Next
    INDEX
    Explanations

    the beginning of new sections or paragraphs in the text

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

    Text followed by "Q:" or a URL

    np_acts-logits-general · gemini-2.0-flash

    returning a request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DoubleQuotes
    -0.80
    +#+#
    -0.74
    UserScript
    -0.66
    fjspx
    -0.66
    EndContext
    -0.66
    IsMutable
    -0.66
    tagHelperRunner
    -0.65
    XmlEnum
    -0.63
    TintMode
    -0.63
    Initializable
    -0.63
    POSITIVE LOGITS
     BoxDecoration
    0.57
    subseteq
    0.53
     useNavigate
    0.53
    ([^
    0.48
    treeview
    0.46
     Audiodateien
    0.46
    ایج
    0.46
     :
    0.45
     useHistory
    0.45
    templateUrl
    0.45
    Activations Density 0.205%

    No Known Activations