© 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. 9-GEMMASCOPE-RES-16K
    11. 9330
    Prev
    Next
    INDEX
    Explanations

    concepts related to destruction and its consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jeografia
    -0.56
    GrantedAuthority
    -0.54
    MigrationBuilder
    -0.54
    LabelTagHelper
    -0.54
    Personendaten
    -0.52
     esternos
    -0.50
     uſed
    -0.48
    ANSA
    -0.48
    neurial
    -0.47
    licants
    -0.47
    POSITIVE LOGITS
     destruction
    1.67
     destroyed
    1.58
     destroy
    1.52
     destroying
    1.51
     destrucción
    1.48
     Destruction
    1.46
     destroys
    1.42
     Destroy
    1.41
    destroy
    1.35
    Destruction
    1.35
    Activations Density 0.293%

    No Known Activations