© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 5582
    Prev
    Next
    INDEX
    Explanations

    expressions of capabilities and possibilities

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

    Followed by "any," "as," or related words

    np_acts-logits-general · gemini-2.0-flash

    any word or phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TargetException
    -0.44
    DrawerLayout
    -0.40
    帖最后由
    -0.39
    })();
    -0.38
     egyes
    -0.37
    ède
    -0.36
    %}
    -0.36
    __()
    -0.35
    ruk
    -0.35
    ständige
    -0.34
    POSITIVE LOGITS
     any
    2.63
     cualquier
    2.30
     qualquer
    2.16
     anything
    2.16
     ANY
    2.14
     qualsiasi
    2.08
    任何
    2.03
     любые
    2.02
     любой
    2.02
    Any
    2.02
    Activations Density 0.948%

    No Known Activations