© 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-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 4970
    Prev
    Next
    INDEX
    Explanations

    phrases describing legal proceedings and events related to crime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 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
    })),
    -0.47
    <eos>
    -0.46
    ]])
    -0.44
    ))),
    -0.43
    ))))
    -0.43
    "])
    -0.42
     welcome
    -0.42
    }))
    -0.42
    ]]
    -0.41
     avenir
    -0.41
    POSITIVE LOGITS
    MLLoader
    0.67
     AssemblyCompany
    0.62
    SBATCH
    0.58
    Tikang
    0.57
    findpost
    0.56
    fillType
    0.54
     snippetHide
    0.54
     jsPsych
    0.54
    GTCX
    0.54
     Italijani
    0.54
    Activations Density 0.946%

    No Known Activations