© 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. 8367
    Prev
    Next
    INDEX
    Explanations

    elements related to pivotal themes or concepts in socio-political contexts

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

    after articles or prepositions

    np_acts-logits-general · gemini-2.0-flash

    core values, broader alliance

    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
    eraard
    -0.71
    ]),
    -0.66
    }),
    -0.64
    ]})
    -0.62
    IsMutable
    -0.61
     "'");
    -0.58
     ligiloj
    -0.57
     popolare
    -0.57
     ModelExpression
    -0.56
     müßte
    -0.56
    POSITIVE LOGITS
     thing
    1.31
     things
    1.12
     stuff
    1.02
     thingy
    0.81
     situation
    0.73
     THING
    0.73
     place
    0.71
     places
    0.70
     guys
    0.69
     guy
    0.69
    Activations Density 0.391%

    No Known Activations