© 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-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 11351
    Prev
    Next
    INDEX
    Explanations

    numerical values and their formats in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.45
     onPostExecute
    -0.45
     HttpNotFound
    -0.40
    <?
    -0.38
    StandardCharsets
    -0.38
     stret
    -0.36
    nalités
    -0.36
    pushFollow
    -0.35
     mCurrent
    -0.35
     ویکی‌پدیا
    -0.35
    POSITIVE LOGITS
    RegressionTest
    0.45
    êques
    0.42
     useAppContext
    0.41
     CanadaChoose
    0.41
    arrings
    0.41
    şil
    0.41
    piers
    0.41
     OMITBAD
    0.41
     nî
    0.40
    Mate
    0.40
    Activations Density 0.694%

    No Known Activations