Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 1185
    Prev
    Next
    INDEX
    Explanations

    colons followed by numerical values or identifiers in code snippets or technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cabul
    -0.81
    imbawa
    -0.69
    mybatisplus
    -0.65
    BagConstraints
    -0.63
    bibinfo
    -0.60
    eſt
    -0.60
     Brow
    -0.60
    Lycka
    -0.59
    mpä
    -0.59
     Chwiliwch
    -0.59
    POSITIVE LOGITS
    :
    2.00
    :
    1.60
    _:
    1.56
    .:
    1.54
    !:
    1.49
    +:
    1.47
     :
    1.44
    ✨:
    1.43
    }:
    1.43
    $:
    1.43
    Activations Density 0.758%

    No Known Activations