© 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. 22-GEMMASCOPE-RES-16K
    6. 15382
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and judicial concepts

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

    preceding a number

    np_acts-logits-general · gemini-2.0-flash

    hyphenated words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */)
    -0.99
    tvguidetime
    -0.92
    });*/
    -0.92
    */;
    -0.90
    ')")
    -0.88
     "));
    -0.88
    Personendaten
    -0.87
    '],
    
    -0.87
    })*/
    -0.87
     }}$}
    -0.85
    POSITIVE LOGITS
     elettrica
    0.52
     üzere
    0.52
    __
    0.48
     acciaio
    0.47
     affari
    0.46
     piú
    0.46
     elettrico
    0.46
     MessageBoxIcon
    0.45
    Sprintf
    0.45
     artistico
    0.44
    Activations Density 0.625%

    No Known Activations