© 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. 2584
    Prev
    Next
    INDEX
    Explanations

    instances of the word "identify" and its variations, indicating a focus on identification processes or actions

    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
    crollView
    -0.61
    Room
    -0.53
    Cruel
    -0.52
    אמ
    -0.49
    música
    -0.48
    UserController
    -0.48
     getPage
    -0.48
     rowCount
    -0.47
     ROOM
    -0.47
    room
    -0.47
    POSITIVE LOGITS
     identify
    1.09
     Identify
    1.05
     identification
    1.05
    Identify
    1.01
    identify
    1.00
     identif
    0.99
     identifies
    0.98
     Identi
    0.96
     identifying
    0.95
     Identification
    0.93
    Activations Density 0.250%

    No Known Activations