© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 57542
    Prev
    Next
    INDEX
    Explanations

    various forms of the phrase "sign up."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.68
    сунок
    -0.64
    ]->
    -0.63
     $"
    -0.58
    gdx
    -0.57
     Houd
    -0.57
    Sprintf
    -0.56
    }:=
    -0.56
    kast
    -0.55
    ):=
    -0.55
    POSITIVE LOGITS
     enrollment
    1.25
     Enrollment
    1.12
     enrolment
    1.11
     Enroll
    1.09
     enroll
    1.09
    Enroll
    1.05
     enrolled
    1.02
    enrollment
    1.01
     registration
    0.99
    Enrollment
    0.98
    Activations Density 0.016%

    No Known Activations