© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5869
    Prev
    Next
    INDEX
    Explanations

    key syntactical elements or punctuation in programming and script code

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

    Code snippets/HTML

    np_acts-logits-general · gemini-2.0-flash

    various languages and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    \
    -0.51
    WebControls
    -0.47
    {$\
    -0.46
     $\
    -0.45
    OpenHelper
    -0.45
    IMPORTED
    -0.44
    </tr>
    -0.44
    tow
    -0.44
    i
    -0.43
    ChildScrollView
    -0.43
    POSITIVE LOGITS
     Bewußt
    0.69
    httphttps
    0.64
     scolaires
    0.63
     Begründung
    0.62
    ſelves
    0.61
    ReusableCell
    0.60
     يتيمه
    0.60
    rsiniz
    0.60
     própri
    0.60
     végétal
    0.59
    Activations Density 0.370%

    No Known Activations