© 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. 11289
    Prev
    Next
    INDEX
    Explanations

    references to reviews or assessments of items or experiences

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

    Follows "give" or includes math operations/variables

    np_acts-logits-general · gemini-2.0-flash

    equations and givens

    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
     …
    -0.84
    etheless
    -0.72
     …”
    -0.70
     Normdatei
    -0.69
    GOTREF
    -0.67
    SequentialGroup
    -0.67
     […]
    -0.66
    principalColumn
    -0.64
     isInitialized
    -0.64
    PYX
    -0.63
    POSITIVE LOGITS
    Rüyada
    0.61
     viață
    0.52
    </b>
    0.52
    </h1>
    0.48
    
    0.48
     InputDecoration
    0.47
    })).
    0.47
    \">
    0.47
    ).\\
    0.46
    )\\
    0.46
    Activations Density 0.470%

    No Known Activations