© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 4694
    Prev
    Next
    INDEX
    Explanations

    terms related to materials and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Carriera
    -0.53
    InstanceState
    -0.48
    md
    -0.45
    醉
    -0.44
    FunctionType
    -0.44
     McKay
    -0.43
     else
    -0.43
    setMsg
    -0.41
    wertig
    -0.41
     It
    -0.40
    POSITIVE LOGITS
    __':
    0.98
    )";
    0.90
     Theſe
    0.90
    Jereo
    0.84
    __':
    0.83
    __":
    0.82
     chré
    0.81
     ViewGroup
    0.78
     nakalista
    0.78
    ]));
    0.76
    Activations Density 2.825%

    No Known Activations