© 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. 2-GEMMASCOPE-RES-16K
    11. 2579
    Prev
    Next
    INDEX
    Explanations

    hash symbols used in various contexts, such as headings or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Enix
    -0.50
    InstanceState
    -0.45
     —,
    -0.44
    ỡng
    -0.44
     ));
    -0.40
    >>();
    -0.40
    ')));
    -0.39
     kaynağından
    -0.38
    )));
    -0.37
     –,
    -0.36
    POSITIVE LOGITS
     #
    3.14
    #
    2.67
     \#
    2.42
     (#
    2.25
    \#
    2.20
     $\#
    2.19
    .#
    2.14
    ＃
    2.09
    -#
    2.09
    :#
    2.02
    Activations Density 0.251%

    No Known Activations