Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10992
    Prev
    Next
    INDEX
    Explanations

    terms related to movement and progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "move" or its variations

    np_acts-logits-general · gemini-2.0-flash

    move or moving to a new place/state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reentrant
    -0.53
    AndPassword
    -0.53
     HasFactory
    -0.52
    +#+
    -0.51
    textTheme
    -0.51
    RTCF
    -0.50
    GraphicsUnit
    -0.50
     sanitarias
    -0.49
    dao
    -0.48
     engraçadas
    -0.48
    POSITIVE LOGITS
     moves
    1.11
     MOVE
    1.09
     MOV
    1.05
     move
    1.03
     Move
    1.01
     moved
    1.00
     Moves
    0.98
     forward
    0.96
     mover
    0.96
     MOVING
    0.96
    Activations Density 0.096%

    No Known Activations