© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 7004
    Prev
    Next
    INDEX
    Explanations

    phrases or terms indicating specific technical parameters or elements such as "shadow", "conductor", and measurement descriptors

    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
    IUrlHelper
    -0.57
     Normdatei
    -0.53
    __*/
    -0.52
     />\
    -0.52
    WebVitals
    -0.51
     صوتيه
    -0.51
    mybatisplus
    -0.51
    exitRule
    -0.50
    Portale
    -0.50
    StoreMessageInfo
    -0.49
    POSITIVE LOGITS
    sh
    1.39
     sh
    1.38
    Sh
    1.32
     Sh
    1.25
    SH
    1.24
    sha
    1.16
     SH
    1.15
    Sha
    1.12
    ash
    1.12
    ASH
    1.07
    Activations Density 2.487%

    No Known Activations