© 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. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 626
    Prev
    Next
    INDEX
    Explanations

    mentions of holiday cottages in Wales and related attractions or activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1145
    +0.12
    0.4%
    313
    +0.08
    0.2%
    757
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.12
    0.04
    1343
    +0.08
    0.04
    1363
    +0.07
    0.03
    Negative Logits
     superintend
    -0.70
     repug
    -0.66
     calum
    -0.64
     cripple
    -0.57
     disprove
    -0.56
     avenge
    -0.55
     banish
    -0.55
     oppress
    -0.54
     subdue
    -0.54
     imprison
    -0.53
    POSITIVE LOGITS
     Mach
    2.79
    Mach
    2.51
     mach
    2.05
     MACH
    1.74
    mach
    1.68
    MACH
    1.52
     quoique
    0.86
    Referencoj
    0.84
     Chan
    0.80
    Sklici
    0.80
    Activations Density 0.298%

    No Known Activations