© 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. 9132
    Prev
    Next
    INDEX
    Explanations

    HTML elements and attributes used in web forms

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

    Tokens before HTML attributes

    np_acts-logits-general · gemini-2.0-flash

    HTML links and options

    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
    QMetaType
    -0.88
     Roskov
    -0.85
    '}),
    -0.85
    ']],
    -0.76
    InitVars
    -0.76
    ⓧ
    -0.76
    ########.
    -0.76
    ])));
    -0.74
    )|^{
    -0.73
     ),
    
    -0.73
    POSITIVE LOGITS
    </strong>
    0.48
    </em>
    0.48
     emp
    0.45
     dessus
    0.44
    ‍
    0.43
     How
    0.42
    towany
    0.41
     Nadu
    0.41
    zieher
    0.40
    OURCE
    0.40
    Activations Density 0.193%

    No Known Activations