© 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. 15-GEMMASCOPE-RES-16K
    6. 5287
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and adaptation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.71
     Accesat
    -0.56
     hänen
    -0.55
    ljeno
    -0.54
    PostExecute
    -0.54
    Gön
    -0.53
     tajam
    -0.51
    aktery
    -0.49
     -,
    -0.49
    viewtopic
    -0.48
    POSITIVE LOGITS
    </h2>
    1.57
    </h4>
    1.37
    </h3>
    1.34
    </h5>
    1.26
    </strong>
    1.22
    </b>
    1.15
    </h1>
    1.11
    </h6>
    1.07
    </u>
    1.01
    }$}
    0.98
    Activations Density 0.756%

    No Known Activations