© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8917
    Prev
    Next
    INDEX
    Explanations

    complex relationships and dependencies between factors in arguments or evidence presented in text

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

    measurement or attributes

    np_acts-logits-general · gemini-2.0-flash

    factors and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jefus
    -0.83
    migrationBuilder
    -0.75
    uxxxx
    -0.73
     Efq
    -0.72
    
    -0.71
     myſelf
    -0.70
     Theſe
    -0.70
     doubtnut
    -0.69
    ]--;
    -0.69
     Monfieur
    -0.68
    POSITIVE LOGITS
     volume
    0.64
     temperature
    0.64
     size
    0.63
     location
    0.62
     physical
    0.61
     age
    0.58
     timing
    0.57
     color
    0.56
     price
    0.56
     weight
    0.56
    Activations Density 1.381%

    No Known Activations