© 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. 21-GEMMASCOPE-RES-16K
    11. 13919
    Prev
    Next
    INDEX
    Explanations

    titles or key phrases related to media, news, or commentary on societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    latego
    -0.47
    jenige
    -0.47
     asesinado
    -0.46
     recevrez
    -0.43
     Infór
    -0.43
     EEUU
    -0.42
     desee
    -0.41
     cuarzo
    -0.40
     esfuer
    -0.40
    eseorang
    -0.40
    POSITIVE LOGITS
    TextHelper
    0.56
     glut
    0.53
    __":
    0.52
    ularity
    0.52
     Xan
    0.51
     metron
    0.51
     lie
    0.50
     unlocking
    0.50
    argout
    0.50
    HEIM
    0.48
    Activations Density 0.227%

    No Known Activations