© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 3793
    Prev
    Next
    INDEX
    Explanations

    terms related to interventions and comparisons between wild-type and mutant varieties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Coo
    -0.93
    Coo
    -0.81
     Tully
    -0.79
     bará
    -0.77
    sejarah
    -0.73
     getLayout
    -0.71
    madrid
    -0.70
    angos
    -0.69
     Tud
    -0.68
    anagh
    -0.68
    POSITIVE LOGITS
    })));
    0.94
     postIndex
    0.84
    protoimpl
    0.83
    onViewCreated
    0.82
     Tribune
    0.79
     Wilder
    0.78
     Strikes
    0.76
    }))
    0.75
     pinulongan
    0.75
    })).
    0.74
    Activations Density 0.130%

    No Known Activations