© 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. 7-GEMMASCOPE-RES-16K
    6. 4249
    Prev
    Next
    INDEX
    Explanations

    expressions related to standing or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })));
    -0.97
    ');?>
    -0.83
    schra
    -0.81
    "?>
    -0.80
     MTL
    -0.73
    UVEN
    -0.72
    theless
    -0.72
    :///
    -0.72
     Petersen
    -0.72
    ;?>
    -0.71
    POSITIVE LOGITS
     STAND
    1.77
     Stands
    1.76
     Stand
    1.71
    Stand
    1.69
     stands
    1.63
    STAND
    1.58
     stand
    1.58
     stood
    1.55
    stands
    1.50
    stand
    1.49
    Activations Density 0.044%

    No Known Activations