© 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. 3-GEMMASCOPE-RES-16K
    11. 8078
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate actions or steps taken in a process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.57
     OMITBAD
    -0.53
    aktery
    -0.52
    UnusedPrivate
    -0.48
     wireType
    -0.47
    ThroughAttribute
    -0.46
    EndInit
    -0.45
     perfección
    -0.44
     صوتيه
    -0.44
     invokingState
    -0.43
    POSITIVE LOGITS
    顺便
    0.53
    就此
    0.53
     Incidentally
    0.52
    newArrayList
    0.52
     pursuit
    0.51
     midst
    0.50
    ついでに
    0.49
    Incident
    0.48
    ついで
    0.48
    одно
    0.47
    Activations Density 0.354%

    No Known Activations