© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8416
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "txt" and related file types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invokingState
    -0.46
     Discharge
    -0.37
     linens
    -0.36
    midos
    -0.35
    gery
    -0.35
    zanne
    -0.35
     cref
    -0.35
     Below
    -0.34
     Registration
    -0.34
     regist
    -0.34
    POSITIVE LOGITS
    TargetException
    0.63
    providedIn
    0.63
     kasarigan
    0.60
     <<<<<<<<<<<<<<
    0.59
     autorytatywna
    0.56
    axios
    0.55
    migrationBuilder
    0.55
    oneofs
    0.54
     snippetHide
    0.53
    fits
    0.53
    Activations Density 0.138%

    No Known Activations